fix Haswell precise store data source encoding

This patch fixes a bug in  precise_store_data_hsw() whereby
it would set the data source memory level to the wrong value.

As per the the SDM Vol 3b Table 18-41 (Layout of Data Linear
Address Information in PEBS Record), when status bit 0 is set
this is a L1 hit, otherwise this is a L1 miss.

This patch encodes the memory level according to the specification.

In V2, we added the filtering on the store events.
Only the following events produce L1 information:
 * MEM_UOPS_RETIRED.STLB_MISS_STORES
 * MEM_UOPS_RETIRED.LOCK_STORES
 * MEM_UOPS_RETIRED.SPLIT_STORES
 * MEM_UOPS_RETIRED.ALL_STORES

Cc: mingo@elte.hu
Cc: acme@ghostprotocols.net
Cc: jolsa@redhat.com
Cc: jmario@redhat.com
Cc: ak@linux.intel.com
Tested-and-Reviewed-by: Don Zickus <dzickus@redhat.com>
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20140515155644.GA3884@quad
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index ae96cfa..980970c 100644 (file)
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -108,15 +108,31 @@ static u64 precise_store_data(u64 status)
        return val;
 }
 
-static u64 precise_store_data_hsw(u64 status)
+static u64 precise_store_data_hsw(struct perf_event *event, u64 status)
 {
        union perf_mem_data_src dse;
+       u64 cfg = event->hw.config & INTEL_ARCH_EVENT_MASK;
 
        dse.val = 0;
        dse.mem_op = PERF_MEM_OP_STORE;
        dse.mem_lvl = PERF_MEM_LVL_NA;
+
+       /*
+        * L1 info only valid for following events:
+        *
+        * MEM_UOPS_RETIRED.STLB_MISS_STORES
+        * MEM_UOPS_RETIRED.LOCK_STORES
+        * MEM_UOPS_RETIRED.SPLIT_STORES
+        * MEM_UOPS_RETIRED.ALL_STORES
+        */
+       if (cfg != 0x12d0 && cfg != 0x22d0 && cfg != 0x42d0 && cfg != 0x82d0)
+               return dse.mem_lvl;
+
        if (status & 1)
-               dse.mem_lvl = PERF_MEM_LVL_L1;
+               dse.mem_lvl = PERF_MEM_LVL_L1 | PERF_MEM_LVL_HIT;
+       else
+               dse.mem_lvl = PERF_MEM_LVL_L1 | PERF_MEM_LVL_MISS;
+
        /* Nothing else supported. Sorry. */
        return dse.val;
 }
@@ -887,7 +903,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
                                data.data_src.val = load_latency_data(pebs->dse);
                        else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST_HSW)
                                data.data_src.val =
-                                       precise_store_data_hsw(pebs->dse);
+                                       precise_store_data_hsw(event, pebs->dse);
                        else
                                data.data_src.val = precise_store_data(pebs->dse);
                }